Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
In embodiments of the present invention, when detecting that user presses shooting key, shooting generates the raw information of photo, and extracts remark information in described voice messaging, be added in the raw information of shooting generation photo by extracting remark information, the photo generated to make shooting carries remark information, solve existing mobile terminal when taking pictures, cannot geographic position be added in photo whenever and wherever possible, reduce the problem of photo browse efficiency, thus when even if mobile terminal is not possessed GPS device or cannot be located by GPS device, user also can add the camera site in remark information in the raw information of picture, occur that if avoid user wants to check the photo taken at certain sight spot, then need to search the situation of this photo page by page by the mode of page turning and traversal photograph album, make user by spot for photography in remark information, search the photo of certain sight spot shooting, improve photo browse efficiency.
embodiment 1
Fig. 1 shows the realization flow of a kind of photographic intelligence adding method that the embodiment of the present invention provides, and details are as follows:
In step S101, acquisition for mobile terminal comprises the voice messaging of remark information, and described remark information comprises the spot for photography of photo, at least one remark information taken in personage, shooting reason;
In the present embodiment, remark information include but not limited to photo spot for photography, shooting personage, shooting reason at least one.
In the present embodiment, acquisition for mobile terminal comprises the voice messaging of remark information, particularly, the sound pick-up outfit voice to user built-in by mobile terminal are sampled, and the simulating signal that obtains of sampling is carried out digital become voice signal, generate voice messaging according to voice signal, the data of voice messaging preserved in the buffer, mobile terminal extracts remark information in voice messaging simultaneously.
As a preferred embodiment of the present invention, when mobile terminal carry out shooting find a view time, obtain and comprise the voice messaging of remark information.
In the present embodiment, when mobile terminal carry out shooting find a view time, camera lens catches image by fixing frame rate, the data of the pixel of original image is preserved in the buffer, and therefrom extracts data carry out image preview on screen.
In the present embodiment, shooting is found a view as trigger condition, by monitoring the broadcast message of system, when listening to the broadcast message of taking and finding a view, represent that mobile terminal to be found a view generation pictures taken by shooting, now, the thread obtaining and comprise the voice messaging of remark information is started, to obtain the voice messaging comprising remark information.
In the present embodiment, for ease of explanation, for practical application, when mobile terminal carry out shooting find a view time, acquisition for mobile terminal comprises the voice messaging of remark information, remark information as got is Great Wall, spot for photography, when detecting that user presses shooting key, shooting generates the raw information of picture A, and in described voice messaging, extract Great Wall, remark information spot for photography, and Great Wall, spot for photography is added in the raw information of shooting generation picture A, the picture A generated to make shooting carries the remark information on Great Wall, spot for photography, be convenient to follow-up according to remark information, carry out searching corresponding picture.
As a preferred embodiment of the present invention,
Obtain the voice messaging comprising remark information, comprising:
The voice messaging of remark information is comprised by the collection of voice messaging collecting device;
In the present embodiment, when mobile terminal comprises the voice messaging of remark information by the collection of voice messaging collecting device, wherein, voice messaging collecting device includes but not limited to sound pick-up outfit, audio player.
In described voice messaging, extract remark information, comprising:
Identify voice messaging, generate remark information list, described remark information list comprises at least one remark information in spot for photography, shooting personage, shooting reason;
In the present embodiment, voice messaging is identified, generate remark information list, the remark information that the interface of mobile terminal shows, because the number of remark information is many, can pass through on interface, to draw a chart, so that user carries out the operation of specifying.
Detect the remark information that user specifies in described remark information list;
In the present embodiment, the remark information that user specifies in remark information list, the mode of specifying includes but not limited to touch or button, by detecting the assigned operation of user, receives the designated result of user.
The remark information of specifying is extracted in voice messaging.
In the present embodiment, user can specify extraction remark information, extracts the remark information of specifying in voice messaging.For ease of explanation, for practical application, when user specifies remark information to be that spot for photography is with when taking personage, only extract corresponding spot for photography and shooting personage in voice messaging, the spot for photography of extracting and shooting personage are added in the raw information of shooting generation photo so that system is follow-up.
In step s 102, when detecting that user presses shooting key, shooting generates the raw information of photo, and extracts remark information in described voice messaging;
In the present embodiment, raw information comprises initial photographing data, camera type, exposure, aperture etc.
In the present embodiment, the raw information that shooting generates photo is prior art, does not repeat at this.
In the present embodiment, remark information is extracted in voice messaging, particularly, hidden Markov method (Hidden Markov Model in the method adopting template matches, HMM) time, a large amount of speech samples is adopted to be that HMM model set up in each entry in advance, and to model training, based on the context-sensitive modeling of coarticulation.Coarticulation, refer to a sound to change by the impact of front and back adjacent tone, be exactly that its characteristic can only gradual change when a sound turns to another sound for the phonatory organ of people from sound generating mechanism, thus make the frequency spectrum under the frequency spectrum of a rear sound and other conditions produce difference.Based on the context-sensitive modeling of coarticulation, avoid the identification interference because coarticulation causes, improve discrimination.When detection has voice messaging to input, carry out pre-service to the voice signal in voice messaging, as stress release treatment, amplifying signal, end-point detection etc., can find out starting point and the end point of voice signal exactly from one section of voice signal by end-point detection.After speech signal pre-processing, feature extraction is carried out to the voice signal of starting point and end point, obtain characteristic parameter sequence, then calculate all speech models in speech model storehouse and generate the probable value of this characteristic parameter sequence, the maximum speech model of probable value is recognition result, obtain the speech model of voice signal in voice messaging, thus identify the content of this section of voice signal in voice messaging.After having identified one section of voice signal, continue to identify next section of voice signal, until to final stage voice signal, thus completed the extraction of remark information.
In step s 103, be added into extracting remark information in the raw information of shooting generation photo, the photo generated to make shooting carries remark information.
In the present embodiment, be added in the raw information of shooting generation photo by extracting remark information, remark information, the photo generated to make shooting carries remark information, is added into extracting remark information the raw information that shooting generates photo.As being added into extracting remark information the raw information that shooting generates photo by the form preset.In the present embodiment, being added into extracting remark information in the raw information of shooting generation photo, being specially:
Obtain the rise time of the raw information of photo;
When the rise time of the raw information of described photo is same preset time period;
Often open in the raw information of photo by what extract that remark information is added into that shooting in same preset time period generates.
In the present embodiment, at the built-in audiomonitor of mobile terminal, the broadcast event in monitoring system, when capturing the broadcast event of rise time of raw information of photo.Being recorded the rise time of the raw information of photo and store, is that row judges that whether the rise time is in same preset time period so that follow-up.
In the present embodiment, preset time period for user is from establishing, also can be able to be system default, limit at this.
In the present embodiment, specifically by a display list, this display list comprises the time period, the zoned format of time period comprises the morning, noon, afternoon, evening, morning, 15 seconds, 25 seconds, 35 seconds, user can specify one or more time period in display list, system, according to the user-selected time period, is added into extracting remark information in the raw information of photo.
In the present embodiment, be added in the raw information of shooting generation photo of same preset time period by extracting remark information, particularly, the raw information of the photo generated is resolved, after parsed, extract the raw information generating photo, and in chronological sequence the raw information of comparison film sorts, adopt and preset addition manner and often open in the raw information of photo by what extract that remark information is added into that shooting in same preset time period generates, generate the file of photo, thus the photo of often opening that the shooting of same preset time period generates all carries remark information, be convenient to user carry out classification by remark information comparison film and call.
In the present embodiment, be added in the raw information of shooting generation photo by extracting remark information, the photo generated to make shooting carries remark information, solve existing mobile terminal when taking pictures, cannot geographic position be added in photo whenever and wherever possible, reduce the problem of photo browse efficiency, thus when even if mobile terminal is not possessed GPS device or cannot be located by GPS device, user also can add the camera site in remark information in the raw information of picture, occur that if avoid user wants to check the photo taken at certain sight spot, then need to search the situation of this photo page by page by the mode of page turning and traversal photograph album, make user by spot for photography in remark information, search the photo of certain sight spot shooting, improve photo browse efficiency.
embodiment 2
Fig. 2 shows embodiment of the present invention preferred embodiment in actual applications, and details are as follows:
S201, prepares to take pictures, and opens voice acquisition switch;
S202, for the photo being about to shooting is explained, carries out speech recognition simultaneously;
S203, presses key of taking pictures and takes pictures, and automatically will close voice simultaneously and obtain switch, stops obtaining voice;
S204, by the voice messaging identified, is set to the remark information etc. of the Exif information of photo, photo files name or photo files;
S205, starts coding, and generates photo files and preserve and to take pictures end.
embodiment 3
Fig. 3 shows the structured flowchart of a kind of photographic intelligence adding set that the embodiment of the present invention provides, this device can run on the various terminals possessing picture pick-up device, include but not limited to mobile phone, pocket computer (Pocket Personal Computer, PPC), palm PC, computing machine, notebook computer, personal digital assistant (Personal Digital Assistant, PDA), MP4, MP3 etc.For convenience of explanation, illustrate only part related to the present embodiment.
With reference to Fig. 3, this photographic intelligence adding set, comprising:
Acquiring unit 31, comprises the voice messaging of remark information for acquisition for mobile terminal, described remark information comprises the spot for photography of photo, at least one remark information taken in personage, shooting reason;
Extraction unit 32, for when detecting that user presses shooting key, shooting generates the raw information of photo, and extracts remark information in described voice messaging;
Adding device 33, for being added into extracting remark information in the raw information of shooting generation photo, the photo generated to make shooting carries remark information.
Further, in this photographic intelligence adding set, described acquiring unit is also for comprising the voice messaging of remark information by the collection of voice messaging collecting device.
Further, in this photographic intelligence adding set, described extraction unit, comprising:
First generates subelement, for identifying voice messaging, generates remark information list, and described remark information list comprises at least one remark information in spot for photography, shooting personage, shooting reason;
Detection sub-unit, for detecting the remark information that user specifies in described remark information list;
Extract subelement, for extracting the remark information of specifying in voice messaging.
Further, in this photographic intelligence adding set, described adding device, comprising:
Obtain subelement, for obtaining the rise time of the raw information of photo;
Second generates subelement, when the rise time for the raw information when described photo is same preset time period;
Add subelement, for often opening in the raw information of photo by what extract that remark information is added into that shooting in same preset time period generates.
The device that the embodiment of the present invention provides can be applied in the embodiment of the method one, two of aforementioned correspondence, and details, see the description of above-described embodiment one, two, do not repeat them here.
In embodiments of the present invention, when detecting that user presses shooting key, shooting generates the raw information of photo, and extracts remark information in described voice messaging, be added in the raw information of shooting generation photo by extracting remark information, the photo generated to make shooting carries remark information, solve existing mobile terminal when taking pictures, cannot geographic position be added in photo whenever and wherever possible, reduce the problem of photo browse efficiency, thus when even if mobile terminal is not possessed GPS device or cannot be located by GPS device, user also can add the camera site in remark information in the raw information of picture, occur that if avoid user wants to check the photo taken at certain sight spot, then need to search the situation of this photo page by page by the mode of page turning and traversal photograph album, make user by spot for photography in remark information, search the photo of certain sight spot shooting, improve photo browse efficiency.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.